© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30680
    Prev
    Next
    INDEX
    Explanations

    interventional, interferometry, interferon

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects medical and scientific terminology related to interventions, interferons, and specific technical procedures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to words built on the prefix “inter,” such as intervention, interventional, interferon, interference, and similar forms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utilização
    -0.98
     Ahnung
    -0.95
     Versuche
    -0.94
    时间的
    -0.94
     welchem
    -0.91
     extensão
    -0.91
     tych
    -0.90
    ickson
    -0.87
     unending
    -0.86
     Grüße
    -0.85
    POSITIVE LOGITS
    ння
    0.91
    Дизайн
    0.90
    SocketAddress
    0.88
     Inter
    0.88
     Bang
    0.87
    
    0.86
     alors
    0.86
    ENSITY
    0.86
     sullo
    0.85
     Putting
    0.84
    Activations Density 0.060%

    No Known Activations